© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 1536
    9. 8-RES_FS1536-JB
    11. 1063
    Prev
    Next
    INDEX
    Explanations

    medical terms and procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.18
    0.9%
    481
    +0.16
    0.8%
    326
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.30
    326
    +0.16
    0.23
    151
    +0.15
    0.18
    Negative Logits
    verbs
    -0.74
    ingham
    -0.66
    vals
    -0.66
    edo
    -0.65
    oho
    -0.64
    activation
    -0.64
    akening
    -0.62
    ebus
    -0.62
    GER
    -0.60
    talk
    -0.60
    POSITIVE LOGITS
    ocument
    0.71
    entimes
    0.71
    wcsstore
    0.68
    ments
    0.63
    ĸļ
    0.62
    antly
    0.62
    hower
    0.62
    igious
    0.61
    emonic
    0.61
    ignty
    0.60
    Activations Density 6.624%

    No Known Activations